README.md

---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
tags:
- role-play
- fine-tuned
- qwen2.5
- mlx
base_model: oxyapi/oxy-1-small
library_name: transformers
---

# ivanfioravanti/oxy-1-small-mlx-4bit

The Model [ivanfioravanti/oxy-1-small-mlx-4bit](https://huggingface.co./ivanfioravanti/oxy-1-small-mlx-4bit) was
converted to MLX format from [oxyapi/oxy-1-small](https://huggingface.co./oxyapi/oxy-1-small)
using mlx-lm version **0.20.1**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("ivanfioravanti/oxy-1-small-mlx-4bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```